Packing/unpacking information generation for efficient generalized kr→r and r→kr array redistribution

Array redistribution is usually required to enhance algorithm performance in many parallel programs on distributed memory multicomputers. Since it is performed at run-time, there is a performance tradeoff between the efficiency of new data decomposition for a subsequent phase of an algorithm and the cost of redistributing data among processors. In this paper, we present efficient methods to generate the packing/unpacking information for BOLCK-CYCLIC(kr) to BLOCK-CYCLIC(r) and BOLCK-CYCLIC(r) to BLOCK-CYCLIC(kr) redistribution with arbitrary source/destination processor sets. The most significant improvement of this paper is that a processor does not need to construct the send/receive data sets for a redistribution. Based on the packing/unpacking information derived from kr→r and r→kr redistributions, a processor can pack/unpack array elements into (from) messages directly. To evaluate the performance of our methods, we have implemented our methods along with the PITFALLS method and the Prylli´s method on an IBM SP2 parallel machine. The experimental results show that our algorithms outperform the PITFALLS method and the Prylli´s method for all test samples